The monograph is intended for specialists in cybersecurity, machine learning, computer linguistics, and artificial intelligence systems, as well as for those obtaining an educational and scientific level of higher education in information technology. The authors consider tools of natural language processing (NLP), machine learning, and deep learning, as well as big data analysis. The monograph presents the results of experiments using various models, including TF-IDF, transform embeddings, SVM and knowledge graphs. The research covers the identification of fake sources in social networks, the development of a set of criteria for detecting sources of disinformation, and the detection of hostile rhetoric, sarcasm and inauthentic behaviour of users in chats. The monograph is supported by the National Research Fund of Ukraine "Information system development for automatic detection of misinformation sources and inauthentic behaviour of chat users", project registration number 33/0012 from 3/03/2025 (2023.04/0012).